{"id":"W4404799249","doi":"10.1007/s11517-024-03247-0","title":"CorLabelNet: a comprehensive framework for multi-label chest X-ray image classification with correlation guided discriminant feature learning and oversampling","year":2024,"lang":"en","type":"article","venue":"Medical & Biological Engineering & Computing","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Oversampling; Discriminative model; Artificial intelligence; Feature (linguistics); Computer science; Pattern recognition (psychology); Machine learning; Correlation; Multi-label classification; Discriminant; Class (philosophy); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004544106,0.0002684277,0.0002909513,0.0001330896,0.0002322586,0.0003221926,0.000422138,0.0003595592,0.000009038558],"category_scores_gemma":[0.001359374,0.0001872488,0.00005475728,0.0004603039,0.0001571965,0.0002038499,0.0002720479,0.0008065185,0.00001139385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006242776,"about_ca_system_score_gemma":0.0000446196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003688126,"about_ca_topic_score_gemma":2.818956e-7,"domain_scores_codex":[0.9982389,0.00004940036,0.0003245096,0.0006953475,0.0002879167,0.0004039845],"domain_scores_gemma":[0.9980241,0.001414133,0.0001059635,0.0002137302,0.00009485782,0.0001471814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003650798,0.000185148,0.005411878,0.000573401,0.0001350969,0.00006159982,0.001154589,0.00405749,0.01939269,0.419935,0.0004865817,0.54857],"study_design_scores_gemma":[0.0003575354,0.0001717259,0.01317427,0.0004906472,0.00001290205,0.00002849469,0.0001689477,0.9806912,0.00009995646,0.0004559831,0.004075228,0.0002731291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02233642,0.001088928,0.9722262,0.002251876,0.0003662053,0.0003302725,0.000002066636,0.001376868,0.00002116082],"genre_scores_gemma":[0.5254693,0.00006265975,0.4742488,0.00006235253,0.000073655,0.00002473585,0.00001988066,0.00001362085,0.00002495749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9766337,"threshold_uncertainty_score":0.7635784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06081812819956545,"score_gpt":0.3265953085034993,"score_spread":0.2657771803039339,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}